© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8044
    Prev
    Next
    INDEX
    Explanations

    code statements ending with semicolon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    emics
    1.15
     trivalent
    1.15
    ówczas
    1.13
    ))+
    1.13
     labile
    1.08
    )=
    1.07
     thermoplastics
    1.06
     extruder
    1.06
     austenite
    1.05
     antifer
    1.05
    POSITIVE LOGITS
    CAB
    2.09
     contributo
    1.97
    Sob
    1.92
     cobertura
    1.88
    WK
    1.87
     Hagan
    1.86
    Roof
    1.84
     Bors
    1.83
    馕
    1.82
     kategori
    1.82
    Activations Density 0.000%

    No Known Activations